mirror of
https://github.com/mudler/LocalAI.git
synced 2026-11-07 13:03:20 -05:00
Stefan Walcz
dcd37a10ef
getAMDGPUMemory only asked rocm-smi. ROCm 7+ images no longer ship it
(only amd-smi, whose Python module is missing in the image), so on an
AMD Strix Halo (gfx1151, ROCm 10.1 image) GET /api/resources returned
"gpus": null and aggregate.gpu_count 0, and the Models page said
"No GPU found. Fit is measured against 122.7 GB of memory" while
inference ran on the GPU.
The amdgpu driver exposes the same figures in sysfs, readable inside the
container:
/sys/class/drm/card0/device/vendor 0x1002
/sys/class/drm/card0/device/mem_info_vram_total 536870912
/sys/class/drm/card0/device/mem_info_vram_used 240300032
/sys/class/drm/card0/device/mem_info_gtt_total 128849018880
/sys/class/drm/card0/device/mem_info_gtt_used 33055911936
When rocm-smi is absent or reports nothing, walk the DRM tree with the
existing scanSysfsGPUs (cardN only, connectors skipped, vendor 0x1002)
and report every card that has mem_info_vram_total. The GPU report is
built by one helper shared with the rocm-smi parser, so the
shared-memory APU rule from #12058 (GTT >= 8x VRAM folds GTT into the
totals) applies identically. GetResourceInfo, GetGPUAggregateInfo and
the fit check all read GetGPUMemoryUsage, so they now see the GPU;
DetectGPUVendor already consulted sysfs.
Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit bf222cadba)
88 lines
2.8 KiB
Go
88 lines
2.8 KiB
Go
package xsysinfo
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
)
|
|
|
|
var _ = Describe("readAMDSysfsGPUMemory", func() {
|
|
var root string
|
|
|
|
BeforeEach(func() {
|
|
root = filepath.Join(GinkgoT().TempDir(), "class", "drm")
|
|
Expect(os.MkdirAll(root, 0o755)).To(Succeed())
|
|
})
|
|
|
|
// Values read inside a ROCm 7+ container on Strix Halo (gfx1151),
|
|
// where rocm-smi is no longer shipped.
|
|
strixHalo := map[string]string{
|
|
"vendor": "0x1002\n",
|
|
"mem_info_vram_total": "536870912\n",
|
|
"mem_info_vram_used": "240300032\n",
|
|
"mem_info_gtt_total": "128849018880\n",
|
|
"mem_info_gtt_used": "33055911936\n",
|
|
}
|
|
|
|
It("reports a shared-memory APU with GTT folded into totals", func() {
|
|
writeSysfsCard(root, "card0", "0000:c5:00.0", strixHalo)
|
|
|
|
got := readAMDSysfsGPUMemory(root)
|
|
Expect(got).To(HaveLen(1))
|
|
Expect(got[0].Vendor).To(Equal(VendorAMD))
|
|
Expect(got[0].Index).To(Equal(0))
|
|
Expect(got[0].TotalVRAM).To(Equal(uint64(536870912 + 128849018880)))
|
|
Expect(got[0].UsedVRAM).To(Equal(uint64(240300032 + 33055911936)))
|
|
Expect(got[0].FreeVRAM).To(Equal(got[0].TotalVRAM - got[0].UsedVRAM))
|
|
Expect(got[0].UsagePercent).To(BeNumerically(">", 0))
|
|
})
|
|
|
|
It("keeps a discrete card on VRAM only", func() {
|
|
writeSysfsCard(root, "card1", "0000:03:00.0", map[string]string{
|
|
"vendor": "0x1002\n",
|
|
"mem_info_vram_total": "25769803776\n",
|
|
"mem_info_vram_used": "1073741824\n",
|
|
"mem_info_gtt_total": "34359738368\n",
|
|
"mem_info_gtt_used": "1048576\n",
|
|
})
|
|
|
|
got := readAMDSysfsGPUMemory(root)
|
|
Expect(got).To(HaveLen(1))
|
|
Expect(got[0].Index).To(Equal(1))
|
|
Expect(got[0].TotalVRAM).To(Equal(uint64(25769803776)))
|
|
Expect(got[0].UsedVRAM).To(Equal(uint64(1073741824)))
|
|
})
|
|
|
|
It("ignores non-AMD cards and connector entries", func() {
|
|
writeSysfsCard(root, "card0", "0000:c5:00.0", strixHalo)
|
|
// A connector hanging off the same device must not count twice.
|
|
Expect(os.MkdirAll(filepath.Join(root, "card0-DP-1"), 0o755)).To(Succeed())
|
|
Expect(os.Symlink(filepath.Join(root, "..", "devices", "pci", "0000:c5:00.0"),
|
|
filepath.Join(root, "card0-DP-1", "device"))).To(Succeed())
|
|
// An NVIDIA card exposing the same attribute names is not ours.
|
|
nv := map[string]string{}
|
|
for k, v := range strixHalo {
|
|
nv[k] = v
|
|
}
|
|
nv["vendor"] = "0x10de\n"
|
|
writeSysfsCard(root, "card1", "0000:01:00.0", nv)
|
|
|
|
got := readAMDSysfsGPUMemory(root)
|
|
Expect(got).To(HaveLen(1))
|
|
Expect(got[0].Index).To(Equal(0))
|
|
})
|
|
|
|
It("reports nothing for an AMD card without mem_info attributes", func() {
|
|
writeSysfsCard(root, "card0", "0000:c5:00.0", map[string]string{
|
|
"vendor": "0x1002\n",
|
|
})
|
|
Expect(readAMDSysfsGPUMemory(root)).To(BeEmpty())
|
|
})
|
|
|
|
It("reports nothing when the DRM tree is missing", func() {
|
|
Expect(readAMDSysfsGPUMemory(filepath.Join(root, "nope"))).To(BeEmpty())
|
|
})
|
|
})
|